DSpace logo

Please use this identifier to cite or link to this item: http://142.54.178.187:9060/xmlui/handle/123456789/18820
Full metadata record
DC FieldValueLanguage
dc.contributor.authorM. T. Jan, Y. Saleem-
dc.date.accessioned2023-03-14T03:48:50Z-
dc.date.available2023-03-14T03:48:50Z-
dc.date.issued2016-09-14-
dc.identifier.citationJan, M. T., & Saleem, Y. (2016). Optical character recognition (ocr) system for saraiki language using neural networks. University of Engineering and Technology Taxila. Technical Journal, 21(3), 106.en_US
dc.identifier.issn2313-7770-
dc.identifier.urihttp://142.54.178.187:9060/xmlui/handle/123456789/18820-
dc.description.abstractSaraiki language is one of the local languages of Pakistan. It is spoken and understood over a large geographical part of Pakistan. Little work has been done to develop Optical Character Recognition systems for local languages due to the complex writing system. The OCR system for Saraiki language can help to digitize the language literature. This work presents an OCR system that uses the Neural Network to recognize the printed text images of Saraiki (Urdu/Arabic/Punjabi) language generated in MS Word. Neural Network is trained with the segmented and isolated character set. At first, characters are extracted from the text image using segmentation approach. These segmented characters are then fed to the Neural Network in order to be recognized. MATLAB is used for the implementation of the OCR system that at present shows about 85% accuracy.en_US
dc.language.isoenen_US
dc.publisherTaxila: University of Engineering and Technology, Taxilaen_US
dc.subjectSaraiki OCR (SOCR)en_US
dc.subjectFeed Forward Neural Networks (FFNN)en_US
dc.subjectMachine Learningen_US
dc.subjectPattern Recognition.en_US
dc.titleOptical Character Recognition (OCR) System For Saraiki Language Using Neural Networksen_US
dc.typeArticleen_US
Appears in Collections:Issue 03

Files in This Item:
File Description SizeFormat 
14-OCR%20System%20for%20Saraiki%20Language%20Using%20Neural%20Networks.htm195 BHTMLView/Open


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.